HV Code: An All-Around MDS Code for RAID-6 Storage Systems
HV Code: An All-Around MDS Code for RAID-6 Storage Systems
复制标题
HV 代码：适用于 RAID-6 存储系统的全能 MDS 代码
DOI：
10.1109/tpds.2015.2464800
复制
发表时间：
2016-06
影响因子：
5.3
通讯作者：
Fu Yingxun
中科院分区：
文献类型：
--
作者：
Shen Zhirong;Shu Jiwu;Fu Yingxun
随着数据规模的不断扩大，大容量存储系统的广泛部署，数据丢失或损坏的概率也在不断上升。RAID-6中的最大距离可分离（Maximum Distance Separable，MDS）码是提高数据可靠性的最佳选择之一，它能以最小的存储需求容忍任意两个磁盘的并发故障。然而，现有的文学作品大多倾向于专业化，在全面的评价下，不能提供令人满意的表现。针对这一问题，本文提出了一种综合利用水平奇偶校验和垂直奇偶校验优点的多尺度码（MDS），称为水平垂直码（HV码）。HV Code实现了完美的I/O平衡并优化了部分条带写入的操作，同时保持了最佳的编码/解码/更新效率。此外，它拥有更短的奇偶校验链，这赠款它能够更有效地恢复单个磁盘故障。HV Code在降级读操作上也表现良好，并通过并行执行四个恢复链来加速双磁盘故障的重建。性能评估表明，HV代码很好地平衡了I/O分布。HV Code还在读-修改-写模式下消除了高达32.2%的部分条带写入I/O操作，并在重建-写模式下减少了高达28.9%的部分条带写入I/O操作。此外，HV Code在单磁盘重建时减少了5.4%~ 39.8%的I/O操作，在降级读操作时减少了8.3%~ 39.0%的I/O操作，在双磁盘恢复时缩短了47.4%~ 59.7%的恢复时间。
The increasing expansion of data scale leads to the widespread deployment of storage systems with larger capacity and further induces the climbing probability of data loss or damage. The Maximum Distance Separable (MDS) code in RAID-6, which tolerates the concurrent failures of any two disks with minimal storage requirement, is one of the best candidates to enhance the data reliability. However, most of the existing works in this literature are more inclined to be specialized and cannot provide a satisfied performance under an all-round evaluation. Aiming at this problem, we propose an all-round MDS code named Horizontal-Vertical Code (HV Code) by taking advantage of horizontal parity and vertical parity. HV Code achieves the perfect I/O balancing and optimizes the operation of partial stripe writes, while preserving the optimal encoding/decoding/update efficiency. Moreover, it owns a shorter parity chain which grants it a more efficient recovery for single disk failure. HV Code also behaves well on degraded read operation and accelerates the reconstruction of double disk failures by executing four recovery chains in parallel. The performance evaluation demonstrates that HV Code well balances the I/O distribution. HV Code also eliminates up to 32.2 percent I/O operations for partial stripe writes in read-modify-write mode, and reduces up to 28.9 percent I/O operations for partial stripe writes in reconstruct-write mode. Moreover, HV Code reduces 5.4~39.8 percent I/O operations per element for the single disk reconstruction, decreases 8.3~39.0 percent I/O operations for degraded read operations, and shortens 47.4~59.7 percent recovery time for double disk recovery.
登录
查看更多内容
DOI：
--
发表时间：
2012-02
期刊：
--
影响因子：
--
作者：
O. Khan;R. Burns;J. Plank;William Pierce;Cheng Huang
通讯作者：
O. Khan;R. Burns;J. Plank;William Pierce;Cheng Huang
DOI：
--
发表时间：
2008-02
期刊：
--
影响因子：
--
作者：
J. Plank
通讯作者：
J. Plank
DOI：
10.1145/1811039.1811054
发表时间：
2010-06
期刊：
--
影响因子：
--
作者：
Liping Xiang;Yinlong Xu;John C.S. Lui;Qian Chang
通讯作者：
Liping Xiang;Yinlong Xu;John C.S. Lui;Qian Chang
DOI：
10.1109/ipdps.2011.78
发表时间：
2011-05
期刊：
2011 IEEE International Parallel & Distributed Processing Symposium
影响因子：
--
作者：
Chentao Wu;Shenggang Wan;Xubin He;Q. Cao;C. Xie
通讯作者：
Chentao Wu;Shenggang Wan;Xubin He;Q. Cao;C. Xie
DOI：
10.1109/msst.2012.6232371
发表时间：
2012-04
期刊：
012 IEEE 28th Symposium on Mass Storage Systems and Technologies (MSST)
影响因子：
--
作者：
Yunfeng Zhu;P. Lee;Yuchong Hu;Liping Xiang;Yinlong Xu
通讯作者：
Yunfeng Zhu;P. Lee;Yuchong Hu;Liping Xiang;Yinlong Xu